© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10581
    Prev
    Next
    INDEX
    Explanations

    all age or physical descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pyrrol
    1.75
    держи
    1.74
    heet
    1.72
    PELL
    1.65
    sic
    1.65
     chartered
    1.64
     weight
    1.64
    )=[
    1.63
    ]+=
    1.62
    andria
    1.61
    POSITIVE LOGITS
    م
    2.29
    adim
    2.11
    м
    2.06
    ්
    1.91
    𝙩
    1.84
    ر
    1.80
     sudd
    1.79
    र
    1.77
    ০০
    1.77
    er
    1.75
    Activations Density 0.061%

    No Known Activations